[Examples] Computing FID in unconditional image generation #9245
Conversation
| if global_step % args.checkpointing_steps == 0: | ||
| if accelerator.is_main_process: |
There was a problem hiding this comment.
I believe both of these could be clubbed together?
Yes, it's a great idea to include clean FID. We could also add an option for |
| @@ -618,6 +647,41 @@ def transform_images(examples): | |||
| save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}") | |||
| accelerator.save_state(save_path) | |||
| logger.info(f"Saved state to {save_path}") | |||
|
|
|||
| # Compute FID | |||
| if args.compute_fid: | |||
There was a problem hiding this comment.
I think because of this line, it's better to keep them separate
|
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
|
@alirezadizaji gentle ping regarding the open comments. |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
What does this PR do?
Since sometimes there's a need for quantitative assessment of image generation, this PR brings an example of FID computation, particularly for unconditional image generation. Using it is quite straightforward: simply by passing the
--compute_fidargument in CLI, now it's possible to log the FID score in the tracker.Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.